Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Nếu
    0.28
    Ⲙ
    0.28
    Якщо
    0.27
    kker
    0.27
    يمه
    0.26
    Тре
    0.26
    Ꭿ
    0.26
    Ⲧ
    0.26
    𝗧
    0.26
    Ⲇ
    0.26
    POSITIVE LOGITS
    s
    0.32
     and
    0.30
     der
    0.24
     tahun
    0.24
    ad
    0.24
     be
    0.24
     pesar
    0.24
    q
    0.23
     रूप
    0.23
     his
    0.23
    Act Density 0.699%

    No Known Activations